* Prepare for archiving of copilot-sdk-java repo in favor of java directory in copilot-sdk
* Update README
* Update with latest `java` from `copilot-sdk`.
### 16:37 Prompt
I have added `copilot-sdk-00` to this VS Code workspace. The `copilot-sdk-00/java` directory **is** the Copilot SDK for which this `copilot-sdk-java.instructions.md` is the instructions.
Do a deep read of the source code in `copilot-sdk-00/java`.
Do a deep read of the existing `copilot-sdk-java.instructions.md`.
Suggest any updates based on what should be changed in `copilot-sdk-java.instructions.md`, based on your findings.
### 16:51 Response
Now I have a comprehensive picture. Let me summarize the findings and suggest updates:
---
Based on my deep read of the Java SDK source code and the current copilot-sdk-java.instructions.md, here are the updates I'd suggest:
## Issues Found
### 1. Incorrect: `session.setModel()` documentation is slightly wrong
The instructions show `session.setModel(modelId)` — this is actually correct (it exists on CopilotSession), but the full signatures should be documented:
- `setModel(String model)`
- `setModel(String model, String reasoningEffort)`
- `setModel(String model, String reasoningEffort, ModelCapabilitiesOverride modelCapabilities)` *(since 1.3.0)*
### 2. Incorrect: `PreToolUseHookOutput` API
The instructions show:
```java
var decision = new PreToolUseHookOutput().setKind("allow");
```
But actually `PreToolUseHookOutput` is a **record** with static factory methods:
- `PreToolUseHookOutput.allow()`
- `PreToolUseHookOutput.deny()`
- `PreToolUseHookOutput.deny(String reason)`
- `PreToolUseHookOutput.ask()`
### 3. Missing: `CopilotClientOptions` fields not documented
These are in the source but not in the instructions:
- `setRemote(boolean)` — Mission Control integration
- `setTelemetry(TelemetryConfig)` — OpenTelemetry export *(since 1.2.0)*
- `setSessionIdleTimeoutSeconds(int)` — Idle timeout *(since 1.3.0)*
- `setExecutor(Executor)` — Custom thread pool
- `setTcpConnectionToken(String)` — TCP security token
### 4. Missing: `ToolDefinition.createSkipPermission()`
A third factory method exists *(since 1.2.0)* that skips the CLI permission request entirely. The instructions only mention `create()` and `createOverride()`.
### 5. Missing: Session listing with filters
The instructions show `client.listSessions()` but don't mention the overload with `SessionListFilter` that can filter by `cwd`, `gitRoot`, `repository`, and `branch`.
### 6. Missing: `session.log()` with URL
The instructions show `log(message, level, ephemeral)` but there's also a 4-param overload:
```java
session.log(String message, String level, Boolean ephemeral, String url)
```
### 7. Missing: MCP Server Configuration
The instructions mention `setMcpServers()` in the SessionConfig options list but don't show how to configure them. There are two types:
- `McpStdioServerConfig` — Local/stdio-based servers
- `McpHttpServerConfig` — HTTP/SSE remote servers
### 8. Missing: Cloud Sessions / Remote features
The `setRemote(boolean)` option on client options and per-session GitHub token support for cloud/content-exclusion scenarios.
### 9. Missing: `ModelCapabilitiesOverride`
Vision/image support can be controlled via model capabilities override, but this isn't documented.
### 10. Missing: `EventErrorPolicy` enum values
The instructions mention `EventErrorPolicy.SUPPRESS_AND_LOG_ERRORS` but don't list the other value: `PROPAGATE_AND_LOG_ERRORS` (which is the default).
### 11. Missing: `onLifecycle()` typed overload
There's also `onLifecycle(String eventType, SessionLifecycleHandler handler)` for filtering specific lifecycle events.
### 12. Minor: `send()` return type
`session.send()` returns `CompletableFuture<String>` (the message ID), which is worth mentioning since it can be used for correlation.
---
## Recommended Priority
**High priority** (incorrect info):
- Fix#2 (`PreToolUseHookOutput` API)
**Medium priority** (missing important features):
- Add #4 (`createSkipPermission`)
- Add #7 (MCP server configuration examples)
- Add #3 (missing client options)
- Add #5 (session list filters)
**Low priority** (nice-to-have completeness):
- Expand #1 (setModel overloads)
- Add #6 (log with URL)
- Add #9-12 (minor additions)
Would you like me to apply any or all of these updates to the file?
### 16:52 Prompt
Yes. Apply all of these.
### 16:54 Response
Created 12 todos
Now I have the full file. Let me apply all the changes:
Starting: *Fix PreToolUseHookOutput API (incorrect)* (1/12)
Replacing 84 lines with 199 lines in [](file:///e%3A/workareas/awesome-copilot-00/instructions/copilot-sdk-java.instructions.md)
```
```
Completed: *Fix PreToolUseHookOutput API (incorrect)* (1/12)
All 12 updates have been applied to copilot-sdk-java.instructions.md:
1. **Fixed** `PreToolUseHookOutput` — now uses correct static factory methods (`allow()`, `deny()`, `ask()`) instead of the incorrect `new PreToolUseHookOutput().setKind("allow")`
2. **Added** `ToolDefinition.createSkipPermission()` section (since 1.2.0)
3. **Added** 5 missing `CopilotClientOptions` fields: `remote`, `telemetry`, `sessionIdleTimeoutSeconds`, `executor`, `tcpConnectionToken`
4. **Added** `SessionListFilter` with `setRepository()`, `setBranch()`, `setCwd()`, `setGitRoot()`
5. **Expanded** `setModel()` to show all 3 overloads (model, reasoning effort, capabilities)
6. **Added** `log(message, level, ephemeral, url)` overload
7. **Added** full MCP server configuration section with `McpStdioServerConfig` and `McpHttpServerConfig` examples
8. **Added** `EventErrorPolicy` enum values with explanations
9. **Added** `onLifecycle(String eventType, handler)` filtered overload
10. **Added** note that `send()` returns `CompletableFuture<String>` (message ID for correlation)
11. **Added** `ModelCapabilitiesOverride` section with vision/limits configuration (since 1.3.0)
12. **Added** `remote` option for Mission Control / cloud session integration
13. **Bonus:** Expanded `SessionHooks` example to include all 5 hook types (`onPreToolUse`, `onPostToolUse`, `onUserPromptSubmitted`, `onSessionStart`, `onSessionEnd`)
Made changes.
### 16:54 Prompt
In the "## Core Principles" section. Add a bullet point that describes how `Optional` is used in the API.
### 16:58 Response
Searched for text `Optional` (`copilot-sdk-00` · `java/src/main/java/com/github/copilot/sdk/json/*.java`), 10 results
Searched for text `Optional` (`copilot-sdk-00` · `java/src/main/java/com/github/copilot/sdk/json/InfiniteSessionConfig.java`), 13 results
Replacing 7 lines with 8 lines in [](file:///e%3A/workareas/awesome-copilot-00/instructions/copilot-sdk-java.instructions.md)
```
```
Added the bullet point describing how `Optional<T>`, `OptionalInt`, and `OptionalDouble` are used on config class getters to distinguish "not set" from explicit values, while setters accept raw types and return `this` for fluent chaining.
Made changes.
### 16:58 Prompt
Consider this code from the Java README.
```java
public class CopilotSDK {
public static void main(String[] args) throws Exception {
var lastMessage = new String[]{null};
// Create and start client
try (var client = new CopilotClient()) { // JDK 25+: comment out this line
// JDK 25+: uncomment the following 3 lines for virtual thread support
// var options = new CopilotClientOptions()
// .setExecutor(Executors.newVirtualThreadPerTaskExecutor());
// try (var client = new CopilotClient(options)) {
client.start().get();
// Create a session
var session = client.createSession(
new SessionConfig().setOnPermissionRequest(PermissionHandler.APPROVE_ALL).setModel("claude-sonnet-4.5")).get();
// Handle assistant message events
session.on(AssistantMessageEvent.class, msg -> {
lastMessage[0] = msg.getData().content();
System.out.println(lastMessage[0]);
});
// Handle session usage info events
session.on(SessionUsageInfoEvent.class, usage -> {
var data = usage.getData();
System.out.println("\n--- Usage Metrics ---");
System.out.println("Current tokens: " + data.currentTokens().intValue());
System.out.println("Token limit: " + data.tokenLimit().intValue());
System.out.println("Messages count: " + data.messagesLength().intValue());
});
// Send a message
var completable = session.sendAndWait(new MessageOptions().setPrompt("What is 2+2?"));
// and wait for completion
completable.get();
}
boolean success = lastMessage[0] != null && lastMessage[0].contains("4");
System.exit(success ? 0 : -1);
}
}
```
I want to get across the very important JDK 25 comment. What's the best place to encode that knowledge in the instructions?
* Apply review suggestions
* Add visual-pr plugin: screenshot capture, annotation, PR embedding, and screen recording
Four skills that teach Copilot to capture UI screenshots (Playwright + PIL),
annotate them with algorithmic label placement, embed before/after images
in PR descriptions, and record animated GIF demos.
Includes demo images showing the annotation engine on GitHub Issues.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Update generated README tables and marketplace.json
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Embed annotate.py module in image-annotations skill
The full working module (annotate_image, grid_image, diff_images) is now
included as a code block so users can save it as annotate.py and import
directly. Scrubbed project-specific labels from examples.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address review feedback: mss.mss() context manager, fix RECT struct, consistent placeholder
- Use mss.mss() context manager instead of mss.MSS() (ui-screenshots, screen-recording)
- Fix broken RECT struct in window+GIF combining example (screen-recording)
- Consistent projectId placeholder in AzDO upload example (pr-screenshots)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fresh pull of updated stage with 2 skills and updated README only
* adjusted skills after feedback and used skill analyser to review
---------
Co-authored-by: Mark Heynes <mutl3y@heynes.biz>
* fix(analyzer): update CWE mappings and terminology to official MITRE standards
* feat(analyzer): integrate CWE 4.20 AI/ML security weaknesses and modern Top 25 view
* fix(analyzer): normalize agent name to match filename and pass validation
* Fixing path on chrome devtools external pluginPath is to the folder in the repo where the plugin structure starts, not where the plugin.json file lives.
* Updating validation scripts and guidance to avoid this mistake again
Adds a new custom agent that guides Azure Verified Modules (AVM) owners through a structured, repeatable workflow to triage open issues across the AVM repos they maintain. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Add new 'Combining Multiple Skills in One Message' subsection to
Chapter 05 (Skills), mirroring upstream commit 5ed858b:
- Multiple skills can be invoked in a single message
- Skill slash commands can appear anywhere in the prompt (not just start)
- Updated lastUpdated to 2026-05-15
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Adds a skill that lets users generate images (icons, sprites, textures,
mockups) directly from their coding workflow using OpenAI gpt-image-2 or
Google Gemini. BYO API key — the skill guides users through setup on
first use.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Replace manual curl/PowerShell download instructions with the
Copilot CLI slash command: /skills add johnpapa/ai-ready
This is simpler, cross-platform, and matches the upstream repo's
install instructions.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The accessibility-report recipe and its companion doc used "assistant.message.delta" (dotted), which never matches the SDK event. The canonical name is "assistant.message_delta" (underscore), as documented in instructions/copilot-sdk-nodejs.instructions.md and used by the Python cookbook. Without this fix the streaming branch was dead and no incremental output was printed.
(cherry picked from commit e050d7bfc96c55924b0bf534c8b3e57359463ba9)
Signed-off-by: syalioune <sy_alioune@yahoo.fr>
The winui plugin from microsoft/win-dev-skills now provides equal-or-better coverage of WinUI 3 development through the winui-dev agent and 7 specialized skills (winui-design, winui-code-review, winui-dev-workflow, winui-packaging, winui-ui-testing, winui-setup, winui-wpf-migration). UWP-to-WinUI 3 API rules are now codified as build-time diagnostics via the Microsoft.WindowsAppSDK.Analyzers Roslyn analyzer.
Co-authored-by: Nikola Metulev <711864+nmetulev@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- copilot-configuration-basics.md: document /fork with optional name (v1.0.47),
origin display in sessions dialog, and read-only gh CLI auto-approval (v1.0.46)
- using-copilot-coding-agent.md: document --resume support for cloud agent
sessions with no pushed changes (v1.0.47)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The REST API for issue field values is simpler and avoids common
pitfalls with the GraphQL approach (needing special headers, node IDs,
option IDs vs names). Key changes:
- Add REST API section as the recommended approach
- Document correct payload format (issue_field_values array wrapper)
- Document that value takes the option NAME not ID for single-select
- List common mistakes (wrong key format, missing wrapper, -f vs --input)
- Move GraphQL to an alternative section (still documented)
- Remove outdated private preview notice (now in public preview)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* feat: add prompt-optimizer skill for enhancing prompt quality in chat interfaces
* Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* fix: update prompt handling to include clarifying questions for incomplete requests
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* feat: add explicit assumption rule and confidence metric to agent documentation
- Add `confidence` field (0‑1) to the output schema in `agents/gem-browser-tester.agent.md`
- Include `confidence` in the `extra` object of `agents/gem-devops.agent.md`
- Append the guideline “State assumptions explicitly; never guess silently” to all agent docs
- Update the “Bisect (Complex Only)” heading to reflect its gate condition
- Minor wording and formatting adjustments across the affected agent documents
* chore: update readme
* chore(release): Streamline agent documentation sections (remove self‑critique steps, renumber Handle Failure/Output)
github-actions[bot]
Mikael
Ed Burns
Jakub Jareš
Sophio Japharidze
Muhammad Ubaid Raza
mutl3y
Burak Kaygusuz
Aaron Powell
Tim Mulholland
Antonio Villanueva
Sebastian Gräf
Copilot
Kaps
Sérgio de Siqueira Silva
JordanSOA
Joseph Counts
Adam
John Papa
syalioune
Tadas Labudis
Nikola Metulev
John Haugabook
Jaylyn Barbee
Tadas Labudis
Antonio Villanueva
Lovy Jain
MUHAMMAD SAMIULLAH
Jim Bennett